What is llm-wiki-agent CLAUDE.md?

A set of instructions for Claude Code to maintain an LLM Wiki, a repository-based knowledge base for language-model projects.

Use it to guide slash commands such as ingesting files, querying wiki content, finding orphan pages or contradictions, and generating relationship diagrams.

It gives the agent defined workflows and page rules for ingesting documents, answering questions, checking wiki health, and building a knowledge graph.

How regexp-lin/llm-wiki-agent configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to regexp-lin/llm-wiki-agent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/regexp-lin/llm-wiki-agent/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/regexp-lin/llm-wiki-agent

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/regexp-lin/llm-wiki-agent/claude-md/github.svg)](https://agentmods.dev/instructions/regexp-lin/llm-wiki-agent/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/regexp-lin/llm-wiki-agent/claude-md"><img src="https://agentmods.dev/badge/instructions/regexp-lin/llm-wiki-agent/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/regexp-lin/llm-wiki-agent/claude-md"><img src="https://agentmods.dev/badge/instructions/regexp-lin/llm-wiki-agent/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,035 This file is loaded in full into every session.

When invoked 1,035 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.01035	$0.01035
Opus 5	$0.00517	$0.00517
Sonnet 5	$0.00207	$0.00207
Haiku 4.5	$0.00103	$0.00103

Measured 9d ago against content hash 977344f299c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

llm-wiki-agent CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LLM Wiki Agent — Claude Code Instructions

This wiki is maintained entirely by Claude Code. No API key or Node.js scripts needed — just open this repo in Claude Code and talk to it.

Slash Commands (Claude Code)

Command	What to say
`/wiki-ingest`	`ingest raw/my-article.md` or just `ingest` (batch mode)
`/wiki-query`	`query: what are the main themes?`
`/wiki-lint`	`lint the wiki`
`/wiki-graph`	`build the knowledge graph`

Or just describe what you want in plain English:

"Ingest this file: raw/papers/attention-is-all-you-need.md"
"Ingest all new files" (batch mode)
"What does the wiki say about transformer models?"
"Check the wiki for orphan pages and contradictions"
"Build the graph and show me what's connected to RAG"

Claude Code reads this file automatically and follows the workflows below.

Wiki Schema

Read WIKI_SCHEMA.md at the project root for the full wiki data model: directory layout, page format, frontmatter, naming conventions, index and log formats.

Ingest Workflow

Single File Mode

Triggered by: "ingest " or /wiki-ingest

Steps (in order):

Read wiki/.ingest-cache.json and compute the source file's SHA256
Check cache: if file is cached and output exists, print "Skipped (cached)" and stop
Read the source document fully using the Read tool
Read wiki/index.md and wiki/overview.md for current wiki context
Write wiki/sources/<slug>.md — use the source page format per WIKI_SCHEMA.md
Update wiki/index.md — add entry under Sources section
Update wiki/overview.md — revise synthesis if warranted
Update/create entity pages for key people, companies, projects mentioned
Update/create concept pages for key ideas and frameworks discussed
Flag any contradictions with existing wiki content
Append to wiki/log.md: ## [YYYY-MM-DD] ingest | <Title>
Update wiki/.ingest-cache.json with the new entry

Use --force to bypass cache.

Read the full file on GitHub · 108 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

9d ago First seen · 108 lines · 1,035 tokens per session scan A 977344f299c9

Subscribe to this mod's changes

llm-wiki-agent CLAUDE.md is an instructions file published in the GitHub repository regexp-lin/llm-wiki-agent (15 stars, last pushed 5mo ago), licensed MIT. It adds 1,035 tokens to every session, about $0.0052 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Building agents Memory and context

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

llm-wiki-agent: Instructions file for Claude Code